How to Use the data.world MCP in CrewAI

Q: How do I connect my CrewAI agents to the data.world MCP server?

For a quick start, just pass the Vinkius URL into the mcps list when defining your Agent. For more control over tools, use the MCPServerHTTP class from crewai.mcp.

Deploy a crew of autonomous agents to research, analyze, and manage your data.world assets with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to CrewAI

Create your Vinkius account to connect data.world to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup data.world with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Data Research Crew

Assign one agent the role of 'Researcher.' Its only job is to use the `search_catalog` tool to find relevant datasets and projects on data.world based on a high-level goal. A second 'Analyst' agent takes the Researcher's findings. It uses `get_dataset_details` and `list_dataset_queries` to dig into the specifics of each asset. This division of labor makes your operation more efficient and targeted.

Automate Project Oversight

Create a 'Project Monitor' agent. Its task is to regularly run `list_my_projects` and `list_project_insights` to keep tabs on progress and new findings across your data.world account. If the Monitor agent detects a change, it passes the information to a 'Notifier' agent, which then takes action. CrewAI's shared memory ensures context is passed seamlessly between agents in the team. This is how you build autonomous oversight.

Your data.world CrewAI MCP Server

Give your CrewAI agents specialized access to data.world. You can equip one agent with read-only tools like `list_my_datasets` and another with more active tools. This MCP Server provides the full set of operations. CrewAI's `tool_filter` lets you selectively expose tools to different agents. Your 'Librarian' agent might only have access to `list_my_collections`, while an 'Auditor' agent can see `list_recent_activity`. It's granular control for your autonomous team.

Setup guide

Set up data.world MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke data.world tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="data.world Analyst",
    goal="Access and analyze data.world data via MCP.",
    backstory="Expert analyst with direct data.world access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent data.world transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="data.world Analyst",
        goal="Access and analyze data.world data via MCP.",
        backstory="Expert analyst with direct data.world access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent data.world transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by data.world. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect data.world now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about data.world MCP in CrewAI

You assign different tools to different agents. For instance, a 'Scout' agent uses `search_catalog` to find datasets. It then passes the dataset IDs to an 'Inspector' agent, which uses `get_dataset_details` to analyze the schema.

Yes, that's a core feature. When setting up your agent with the `MCPServerHTTP` tool provider, use the `tool_filter` argument. This lets you create specialized agents that can only perform specific data.world actions.

It does. You can set up your crew to work sequentially, where one agent's output is the next one's input. Or you can use a hierarchical model, where a manager agent delegates data.world tasks to subordinate agents.

For a quick start, just pass the Vinkius URL into the `mcps` list when defining your Agent. For more control over tools, use the `MCPServerHTTP` class from `crewai.mcp`.

Only the metadata your agents are explicitly told to access. This includes things like dataset schemas from `get_dataset_details` or project member lists from `get_project_details`. The connection is managed by Vinkius, and each agent's tool execution runs in an isolated, zero-trust environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript